Official platform of Tsinghua Big Data Research Center, sharing the team's latest research, teaching updates, and big data news.
OpenAI’s new GPT‑5.6 Prompt Guidance shows that trimming redundant system instructions can boost agent performance by up to 15 % while cutting token usage by more than half, and it provides a step‑by‑step methodology for simplifying prompts, defining outcome‑first instructions, managing tools, and verifying results.
This article presents ten practical AI agent workflow templates, each with a trigger, context, tools, decision rules, and human checkpoints, showing how to automate tasks like email triage, research briefs, form filling, meeting minutes, support routing, content repurposing, competitor monitoring, invoice reconciliation, CRM updates, and QA review.
In an eight‑day, fully automated experiment, Weco’s AIDE² system ran 100 outer‑loop iterations without updating model weights, rewrote its own harness, produced two standout versions (AIDE₄₇ and AIDE₈₅) that outperformed human‑tuned baselines on three unseen benchmarks, and cut reward‑hacking rates from 63% to 34%, providing the first Level‑1 evidence of recursive self‑improvement.
The article argues that AI has become a national strategic priority and a mandatory driver of enterprise transformation, outlining the shift from digitalization to digital intelligence, the anxieties CEOs face, and a seven‑point framework for leaders to become effective chief digital intelligence officers.
The UC Berkeley 2025 PhD thesis by Linyuan Gong demonstrates that large language models for code must learn program structure—legal positions, complete units, and semantic constraints—through a series of code‑structure‑aware techniques, improving translation, completion, repair, and generation tasks.
Thariq, a core member of Anthropic’s Claude Code team, shows that removing more than 80% of system prompts from Claude 5 models yields no measurable loss in coding benchmarks, prompting a fundamental shift in prompt‑engineering practices.
This survey reviews continual self‑supervised learning (CSSL) for vision models, explaining why self‑supervised objectives better resist forgetting, outlining evaluation protocols, categorizing six CSSL method families, and discussing challenges such as unified benchmarks, large‑scale models, and multimodal drift.
The article reviews DeepMind’s “LLMs can’t jump” paper, arguing that even if large language models are fed all scientific knowledge up to 1905, they still cannot recreate Einstein’s breakthrough because they lack the abductive jump from physical intuition to new axioms, a capability that requires interactive world models and physical priors.
The article reviews recent AI agent research, exposing three structural paradoxes—memory, reasoning, and evolution—each illustrated with concrete systems, benchmarks, and safety studies, and argues that only coordinated progress across all three dimensions can yield truly mature, self‑improving agents.
Recent research introduces the Shared Embodied Intelligence framework, integrating a biomechanical human model with robot hardware and control systems to co‑optimize design, enabling the ergoCub humanoid robot to adapt its motions in real time for safer, more efficient human‑robot collaboration, as demonstrated in load‑lifting and disturbance‑rejection experiments.
